Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5170 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8709. Min Act: -0.1700
Data Index: 5087713 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 7294983 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 1744366 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 8391821 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 7159036 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 2791959 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4647. Min Act: -0.1700
Data Index: 8095189 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.3709. Min Act: -0.1700
Data Index: 2519666 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.3709. Min Act: -0.1700
Data Index: 5458261 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.3397. Min Act: -0.1700
Data Index: 3317411 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 2445621 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 3515233 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 936150 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 6576328 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 5433942 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2772. Min Act: -0.1700
Data Index: 4464539 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2459. Min Act: -0.1700
Data Index: 516339 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2147. Min Act: -0.1700
Data Index: 7755841 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.2147. Min Act: -0.1700
Data Index: 1794669 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.1834. Min Act: -0.1700
Data Index: 4280999 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19